Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    loc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /perl
    -0.06
     Sauce
    -0.06
    окрем
    -0.06
     ATM
    -0.06
    Equipment
    -0.06
    PJ
    -0.06
    INST
    -0.06
     případ
    -0.06
     Authentic
    -0.06
     fleets
    -0.06
    POSITIVE LOGITS
    /Common
    0.07
     underage
    0.06
     zwe
    0.06
    ocumented
    0.06
     mit
    0.06
    617
    0.06
     Janeiro
    0.06
     nombre
    0.06
     كما
    0.06
    Dr
    0.06
    Act Density 0.006%

    No Known Activations